Hola,
¿eres nuevo aquí?

Regístrate gratis y conecta tu empresa con financiación pública, partners y proyectos.

Tengo cuenta

Regístrate

Ver video

DECOLLAGE

Financiado

DEep COgnition Learning for LAnguage GEneration

In recent years, transformer-based deep learning models such as BERT or GPT-3 have led to impressive results in many natural language processing (NLP) tasks, exhibiting transfer and few-shot learning capabilities. However, despit... ver más

31/07/2028

2M€

Presupuesto del proyecto: 2M€

Líder del proyecto

INSTITUTO DE TELECOMUNICACOES No se ha especificado una descripción o un objeto social para esta compañía.

TRL 4-5

Ver 2 Participantes

Financiación concedida El organismo HORIZON EUROPE notifico la concesión del proyecto el día 2023-04-05

ERC-2022-COG: ERC CONSOLIDATOR GRANTS Scope:Objectives

I+D

Cerrada hace 2 años

0% 100% 100%

2 Participantes

1.79M€ | Lider

Unbabel

209.38K€ | Participante

Conecta tu I+D

¿Tienes un proyecto y buscas un partner? Gracias a nuestro motor inteligente podemos recomendarte los mejores socios y ponerte en contacto con ellos. Te lo explicamos en este video

Proyectos interesantes

ExplainYourself Explainable and Robust Automatic Fact Checking 1M€ Cerrado

PID2021-126061OB-C41 BEWORD-UPV: DESCUBRIENDO EL SIGNIFICADO Y LA INTENCION MAS A... 121K€ Cerrado

TENACITY Tensors and Neural Networks for Computational Creativity 2M€ Cerrado

PID2019-104512GB-I00 LANGUAGE UNDERSTANDING TEST SETS 36K€ Cerrado

PID2019-107579RB-I00 ARQUITECTURAS AVANZADAS DE APRENDIZAJE PROFUNDO APLICADAS AL... 271K€ Cerrado

PID2021-123956OB-I00 GENERACION CONSCIENTE DE TEXTOS 145K€ Cerrado

Duración del proyecto: 63 meses Fecha Inicio: 2023-04-05
Fecha Fin: 2028-07-31

Líder del proyecto

INSTITUTO DE TELECOMUNICACOES No se ha especificado una descripción o un objeto social para esta compañía.

TRL 4-5

Presupuesto del proyecto 2M€

Descripción del proyecto In recent years, transformer-based deep learning models such as BERT or GPT-3 have led to impressive results in many natural language processing (NLP) tasks, exhibiting transfer and few-shot learning capabilities. However, despite faring well in benchmarks, current deep learning models for NLP often fail badly in the wild: they are bad at out-of-domain generalization, they do not exploit contextual information, they are poorly calibrated, and their memory is not traceable. These limitations stem from their monolithic architectures, which are good for perception, but unsuitable for tasks requiring higher-level cognition. In this project, I attack these fundamental problems by bringing together tools and ideas from machine learning, sparse modeling, information theory, and cognitive science, in an interdisciplinary approach. First, I will use uncertainty and quality estimates for utility-guided controlled generation, combining this control mechanism with the efficient encoding of contextual information and integration of multiple modalities. Second, I will develop sparse and structured memory models, together with attention descriptive representations towards conscious processing. Third, I will build mathematical models for sparse communication (reconciling discrete and continuous domains), supporting end-to-end differentiability and enabling a shared workspace where multiple modules and agents can communicate. I will apply the innovations above to highly challenging language generation tasks, including machine translation, open dialogue, and story generation. To reinforce interdisciplinarity and maximize technological impact, collaborations are planned with cognitive scientists and with a scale-up company in the crowd-sourcing translation industry.

Conecta tu I+D

Entra hoy

¿Olvide mi contraseña?

Financiación

Empresas

CTIs/Universidades

Proyectos

Investigadores